Think of it as a kind of (theoretical) ‘upper bound’ on the problem. None of the actual computable (i.e. on real-world computers built by humans) approximations to AIXI are very good in practice.
The AIXI thing was a joke; a Bayesian update on low-level physics with unknown initial conditions would be superexponentially slow, but it certainly isn’t uncomputable. And the distinction does matter—uncomputability usually indicates fundamental barriers even to approximation, whereas superexponential slowness does not (at least in this case).
No, he’s referring to something like performing a Bayesian update over all computable hypotheses – that’s incomputable (i.e. even in theory). It’s infinitely beyond the capabilities of even a quantum computer the size of the universe.
Think of it as a kind of (theoretical) ‘upper bound’ on the problem. None of the actual computable (i.e. on real-world computers built by humans) approximations to AIXI are very good in practice.
The AIXI thing was a joke; a Bayesian update on low-level physics with unknown initial conditions would be superexponentially slow, but it certainly isn’t uncomputable. And the distinction does matter—uncomputability usually indicates fundamental barriers even to approximation, whereas superexponential slowness does not (at least in this case).